CN117634926B

CN117634926B - Comprehensive port operation prediction method and system based on big data analysis

Info

Publication number: CN117634926B
Application number: CN202311679542.1A
Authority: CN
Inventors: 丁格格; 李春旭; 耿雄飞; 文捷; 刘东华; 李益琴; 刘雨; 王月竹; 李明
Original assignee: China Waterborne Transport Research Institute
Current assignee: China Waterborne Transport Research Institute
Priority date: 2023-12-08
Filing date: 2023-12-08
Publication date: 2024-06-04
Anticipated expiration: 2043-12-08
Also published as: CN117634926A

Abstract

The invention discloses a comprehensive port operation prediction method and a system based on big data analysis, comprising the following steps: acquiring target port service information, and carrying out throughput prediction according to the target port service information to obtain throughput prediction information; acquiring port cargo information, analyzing cargo accumulation conditions through the port cargo information, and carrying out ship loading and unloading planning according to analysis results; constructing a digital map of the target port, and planning a transportation route and formulating an equipment scheduling scheme according to the digital map of the target port; acquiring throughput prediction information, predicting the target port camp and analyzing the resource utilization, and recommending the operation direction; acquiring operation direction recommendation information, carrying out situation analysis on a target port, and carrying out pricing analysis on the operation recommendation direction. Accurate operation prediction is provided, resource allocation is optimized, and operation efficiency and high port competitiveness are improved so as to meet the requirements of different ports and changing market environments.

Description

Comprehensive port operation prediction method and system based on big data analysis

Technical Field

The invention relates to the technical field of port operation prediction, in particular to a comprehensive port operation prediction method and system based on big data analysis.

Background

Port operations are a critical component of global trade and logistics, playing a vital role in international trade and economic growth. However, the conventional port operation management method has obvious disadvantages in coping with complex market environments and dynamic demands. Conventional methods generally rely on static models and rules of thumb, which are difficult to deal with factors such as throughput, loading and unloading requirements, resource allocation, and market variation. This results in problems of resource waste, handling and stacking, transportation congestion, inefficiency, etc. The rise of big data analysis technology provides great opportunities for port operations. Big data analysis techniques may help port managers better understand and handle factors such as throughput, loading and unloading requirements, resource allocation, and market changes to maximize revenue, reduce cost, and improve quality of service. By integrating various data sources, including throughput data, cargo information, loading and unloading equipment status, traffic information, market trends, etc., port managers can achieve improvements in aspects of throughput prediction, resource allocation, loading and unloading equipment scheduling, market trend analysis, revenue prediction, etc. Thereby helping port operation manager to make better decision, improving port efficiency and competitiveness.

Disclosure of Invention

The invention overcomes the defects of the prior art, and provides a comprehensive port operation prediction method and system based on big data analysis, which aim at improving port operation efficiency and competitiveness.

In order to achieve the above object, the first aspect of the present invention provides a comprehensive port operation prediction method based on big data analysis, including:

Acquiring target port service information, and carrying out throughput prediction according to the target port service information to obtain throughput prediction information;

acquiring port cargo information, analyzing cargo accumulation conditions through the port cargo information, and carrying out ship loading and unloading planning according to analysis results;

Constructing a digital map of the target port, and planning a transportation route and formulating an equipment scheduling scheme according to the digital map of the target port;

acquiring throughput prediction information, predicting the target port camp and analyzing the resource utilization, and recommending the operation direction;

acquiring operation direction recommendation information, carrying out situation analysis on a target port, and carrying out pricing analysis on the operation recommendation direction.

In this scheme, the obtaining the service information of the target port, and predicting throughput according to the service information of the target port specifically includes:

acquiring target port service information, and performing feature extraction on the target port service information to obtain port service feature information;

constructing a throughput prediction model based on a gray prediction model and a particle swarm optimization algorithm, and performing deep learning and training on the throughput prediction model;

Inputting the port service characteristic information into the throughput prediction model for analysis, and generating an initial prediction result according to the port service characteristic information to obtain initial prediction information;

Constructing an objective function according to the sum of average relative errors, generating an initial particle swarm according to initial prediction information, calculating an adaptability value of an initial particle swarm individual, judging with a preset threshold value, and updating the position and the speed according to a judging result;

acquiring updated particle swarms, extracting individual optimal fitness and global optimal fitness, carrying out optimizing search, calculating fitness values of the searched particles, and carrying out comparative analysis to obtain optimized fitness information;

the optimized fitness information comprises individual optimal fitness and global optimal fitness, the optimized fitness information is respectively judged with the individual fitness and the global fitness, and iterative updating is carried out according to a judgment result;

And acquiring final fitness information, extracting corresponding particles according to the optimal fitness information, and optimizing initial prediction information to obtain throughput prediction information by taking the particles as optimization weights.

In this scheme, acquire harbour cargo information, through harbour cargo information analysis cargo accumulation condition carries out the shipping loading and unloading planning according to the analysis result, specifically does:

acquiring port cargo information and throughput prediction information, wherein the port cargo information comprises: port cargo accumulation area information, port cargo accumulation time information, port cargo accumulation quantity information and port cargo type information;

Extracting attributes of the port cargo information, and extracting accumulation time and quantity, cargo types and accumulation areas to obtain port cargo attribute information;

analyzing the stacking condition according to the port cargo attribute information, and calculating the ratio of the cargo stacking area to the storable cargo area to be used as the cargo stacking rate;

Dividing cargoes according to stacking time based on a clustering algorithm, dividing corresponding cargoes types and quantity into corresponding stacking time types, and performing stacking condition analysis by combining a classification result and a cargo stacking rate to obtain stacking condition analysis information;

Acquiring target port service information, performing feature extraction on the target port service information, and extracting port entering ship information and port entering ship cargo information to obtain port ship feature information;

presetting three evaluation indexes of ship attribute, cargo type and delivery information, respectively setting corresponding weights, carrying out weighted calculation by combining the port ship characteristic information, and carrying out priority evaluation according to a weighted calculation result to obtain priority evaluation information;

And carrying out ship loading and unloading planning by combining the priority evaluation information, the port ship characteristic information and the stacking condition analysis information to obtain loading and unloading planning information.

In this scheme, the construction of the digital map of the target port, carrying out the transportation route planning and the equipment scheduling scheme formulation according to the digital map of the target port, specifically comprises:

Acquiring geographic information of a target port area based on a remote sensing technology, and constructing a digital map of the target port through a GIS system, wherein the digital map comprises a topographic map of the port area, a road map of the port area and a facility map of the port;

acquiring loading and unloading planning information and harbour equipment information, performing feature extraction on the loading and unloading planning information, and extracting the attribute and the volume of goods in each planning time period to obtain loading and unloading planning feature information;

According to the equipment working attribute of the harbour equipment information, calculating the Euclidean distance between loading and unloading planning characteristic information and the equipment working attribute, and carrying out correlation analysis to obtain correlation analysis information;

combining the correlation analysis information, the loading and unloading planning information and the digital map of the target port to formulate a device scheduling scheme;

constructing a route planning model based on a distributed path planning algorithm, inputting an equipment scheduling scheme and loading and unloading planning information into the route planning model, and carrying out transportation route planning by combining a digital map of a target port to obtain transportation route planning information;

Acquiring real-time transportation information according to the transportation route planning information, analyzing the path situation through the real-time transportation information, calculating the transportation flow in each area in unit time, and judging with a preset threshold value to obtain the path situation analysis information;

Congestion diversion is carried out according to the path condition analysis information, a route of a subsequent passing through a congested road section is obtained, the transportation flow of a nearby area is extracted, and self-adaptive path replacement is carried out by combining a digital map of a target port to obtain diversion route information;

And sending the diversion route information to each transport device, marking the congestion road section and guiding the diversion route by combining a digital map, and performing visual processing.

In this scheme, the obtaining of the throughput prediction information, the target port revenue prediction and the resource utilization analysis, and the operation direction recommendation specifically include:

Acquiring an equipment scheduling scheme, transportation route planning information, port personnel information and accumulation condition analysis information, and calculating port operation cost to obtain port operation cost information;

acquiring throughput prediction information, constructing a port camp prediction model, and inputting port operation cost information and the throughput prediction information into the port camp prediction model for prediction to obtain port camp prediction information;

Performing resource utilization analysis according to the accumulation condition analysis information and the equipment scheduling scheme, and calculating the accumulation site and the equipment utilization rate to obtain resource utilization analysis information;

acquiring port service information in unit time, performing feature extraction, extracting port service attributes and cargo attributes, and obtaining port service attribute feature information;

carrying out main service evaluation on the port service attribute characteristic information based on a statistical algorithm, and analyzing the occurrence frequency of various attribute services as an evaluation index to obtain main service evaluation information;

acquiring port attribute information, and carrying out operation direction analysis by combining the main service evaluation information and the resource utilization analysis information to obtain candidate operation direction analysis information;

Acquiring port equipment information, retrieving and acquiring demand equipment information based on big data through the candidate operation direction analysis information, and comparing and analyzing the port equipment information and the demand equipment information to obtain demand equipment adaptation analysis information;

and carrying out the usability evaluation on each candidate operation direction according to the required equipment adaptation analysis information, and selecting a final recommended operation direction according to an evaluation result to obtain operation direction recommendation information.

In this scheme, obtain operation direction recommendation information, carry out the situation analysis to the target harbour to carry out pricing analysis to operation recommendation direction, specifically do:

Acquiring port daily operation information, inputting port daily operation analysis information into a throughput prediction model, and predicting the maximum throughput as a prediction index to obtain maximum throughput prediction information;

Acquiring port service range information and historical operation information, respectively extracting characteristics, and extracting service attributes, historical operation directions and benefits of each operation direction to obtain port operation characteristic information;

Acquiring historical customer information and competing harbor information, and respectively calculating attention scores of all influence factors based on a multi-head attention mechanism combined with the historical customer information and competing harbor information, presetting three attention heads of position, time and cost, and evaluating the attention scores as influence factor evaluation indexes to obtain influence factor evaluation information;

Performing SWOT analysis on the target port according to the influence factor evaluation information, the historical customer information, the competing port information and the port operation characteristic information based on the situation analysis method to obtain situation analysis information;

Constructing a pricing game model, acquiring competition demand information, constructing a game objective function according to the competition demand information, inputting operation direction recommendation information, influence factor evaluation information, situation analysis information and maximum throughput prediction information into the pricing game model, and performing pricing strategy analysis;

And presetting a reaction function, carrying out market reaction simulation on the obtained pricing strategies, analyzing market reactions of different strategies, judging with a preset threshold value, and selecting a final pricing strategy according to a judgment result to obtain final pricing strategy information.

The second aspect of the present invention provides a comprehensive port operation prediction system based on big data analysis, the system comprising: the comprehensive port operation prediction method based on big data analysis comprises a memory and a processor, wherein the memory contains a comprehensive port operation prediction method program based on big data analysis, and when the comprehensive port operation prediction method program based on big data analysis is executed by the processor, the following steps are realized:

The invention discloses a comprehensive port operation prediction method and a system based on big data analysis, comprising the following steps: acquiring target port service information, and carrying out throughput prediction according to the target port service information to obtain throughput prediction information; acquiring port cargo information, analyzing cargo accumulation conditions through the port cargo information, and carrying out ship loading and unloading planning according to analysis results; constructing a digital map of the target port, and planning a transportation route and formulating an equipment scheduling scheme according to the digital map of the target port; acquiring throughput prediction information, predicting the target port camp and analyzing the resource utilization, and recommending the operation direction; acquiring operation direction recommendation information, carrying out situation analysis on a target port, and carrying out pricing analysis on the operation recommendation direction. Providing accurate operation prediction, optimizing resource allocation, improving operation efficiency and high port competitiveness to meet the demands of different ports and changing market environment

Drawings

In order to more clearly illustrate the technical solutions of embodiments or examples of the present invention, the drawings that are required to be used in the embodiments or examples of the present invention will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive efforts for those skilled in the art.

FIG. 1 is a flowchart of a comprehensive port operation prediction method based on big data analysis according to an embodiment of the present invention;

FIG. 2 is a flow chart of a pricing strategy according to one embodiment of the invention;

FIG. 3 is a block diagram of a comprehensive port operation prediction system based on big data analysis according to an embodiment of the present invention;

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.

as shown in fig. 1, the present invention provides a comprehensive port operation prediction method flowchart based on big data analysis, which includes:

S102, acquiring target port service information, and carrying out throughput prediction according to the target port service information to obtain throughput prediction information;

It should be noted that, through carrying out feature extraction to the service information of the target port, obtain the service features of the target port, including port goods, port orders, service ship arrival port time and other service features, through inputting port feature information into the throughput prediction model for preliminary prediction generation, optimize the preliminary prediction result according to the particle swarm algorithm, calculate the local optimal solution and the global optimal solution and carry out iterative optimization, finally obtain the optimal fitness, extract the particles corresponding to the optimal fitness, as the optimization weight, optimize the initial prediction information, obtain the throughput prediction information, improve the accuracy of the throughput prediction, more clearly show the throughput of the target port on a single day or multiple days and the throughput of each time period, and facilitate operation arrangement and management.

S104, acquiring port cargo information, analyzing cargo accumulation conditions through the port cargo information, and carrying out ship loading and unloading planning according to analysis results;

It should be noted that, first, cargo information of a port is acquired, including cargo accumulation area, accumulation time, accumulation number and cargo type. Meanwhile, throughput prediction information is prepared to know the throughput of each time period in the future of the port. And extracting attributes of port cargo information, converting the port cargo information into structural data, including stacking time, number, cargo type, stacking area and the like, and forming characteristic information of the cargo. And then, calculating the ratio of the cargo accumulation area to the storable cargo area based on the cargo attribute information so as to obtain the cargo accumulation rate and reflect the cargo accumulation degree. And dividing the cargoes according to the stacking time by using a clustering algorithm, dividing the cargoes into different stacking time types, and simultaneously considering the types and the quantity of the cargoes to obtain detailed stacking condition analysis information. Then, the port entering ship information and port entering ship cargo information of the target port are acquired, wherein the port entering ship information and the port entering ship cargo information comprise ship types, cargo types, quantity, delivery information and the like, the characteristics of the information are extracted to construct port ship characteristic information, and three evaluation indexes are preset: the ship attribute, the cargo type and the delivery information, and corresponding weights are respectively set for each evaluation index. And then, carrying out weighted calculation by combining the characteristic information of the port ships to obtain priority evaluation information of each ship, wherein the priority evaluation information reflects the loading and unloading priorities of the ships. And carrying out ship loading and unloading planning by combining the priority evaluation information, the port ship characteristic information and the stacking situation analysis information, wherein the ship loading and unloading planning comprises the steps of determining which ship loads and loads are loaded and unloaded first, and processing the loads to reduce stacking to the greatest extent, improve efficiency and ensure that the delivery requirements of different loads are met.

Further, accumulation condition analysis information and goods warehouse-in information are obtained, goods tracing is carried out according to the goods warehouse-in information, storage service information and customer information of target accumulated goods are extracted, and accumulated goods tracing information is obtained; calculating accumulation duration information of each cargo according to the cargo warehousing time information, analyzing the accumulation time limit of the cargo by combining the accumulation cargo traceability information, judging whether the cargo is overdue or approaching the time limit, and generating cargo storage early warning information; according to the goods storage early warning information and the goods tracing information, overdue reminding is carried out on the goods attribution user, and the continuous storage service is recommended; acquiring disaster weather information, constructing a disaster influence prediction model, and inputting the disaster weather information into the disaster influence prediction model to obtain disaster influence prediction information; acquiring a digital map of the target port, and carrying out disaster area analysis by combining the disaster prediction information to obtain disaster area analysis information; analyzing the cargo accumulation condition and the type of the disaster area according to the disaster area analysis information, the cargo warehouse-in information and the accumulation condition analysis information to obtain cargo condition information of the disaster area; extracting attributes according to cargo condition information of a disaster area, extracting cargo attributes, judging whether the cargo is a cargo which is easy to be affected, and obtaining cargo disaster influence analysis information; planning a cargo migration area according to cargo accumulation condition information and disaster area analysis information, and planning a migration route by combining a digital map of a target port to obtain cargo migration scheme information; and migrating the target goods according to the goods migration scheme information, ensuring the safety of the goods in the disaster environment, ensuring the property safety of the port and the clients, and simultaneously improving the safety of the port so as to improve the market competitiveness of the port.

S106, constructing a digital map of the target port, and planning a transportation route and making an equipment scheduling scheme according to the digital map of the target port;

It should be noted that, first, geographical information of a target port area including topography, roads, facilities, and the like is acquired by using a remote sensing technology. And constructing a digital map of the target port by using a GIS system, wherein the digital map comprises a topography map, a road map and a port facility map so as to realize the visualization of geographic information. Next, loading and unloading planning information is acquired, including the attribute and the volume of the goods in different time periods, so as to know loading and unloading requirements. Harbour site information is obtained, including the operational attributes of the equipment, such as operational speed, handling capacity, etc. And extracting characteristics of the loading and unloading planning information to construct loading and unloading planning characteristic information, calculating Euclidean distance based on equipment working attributes and the loading and unloading planning characteristic information, and carrying out correlation analysis to know the correlation between the loading and unloading planning and the equipment attributes. And then, combining the correlation analysis information, the loading and unloading planning information and the digital map, and making an equipment scheduling scheme so as to optimize the use of loading and unloading equipment and improve the efficiency. The method comprises the steps of constructing a route planning model of a distributed route planning algorithm, inputting a device scheduling scheme and loading and unloading planning information into the route planning model, carrying out transportation route planning by combining a digital map, distributing tasks for each node by dividing a transportation route into different nodes, and enabling each node to be responsible for planning a path and a transportation task of a local area of the node so as to determine an optimal cargo transportation path. Coordination of intersections, cargo junctions, and handling equipment is considered to ensure orderly and efficient flow of cargo within the port, thereby obtaining transportation route planning information. Real-time transportation information, including vehicle position, speed, etc., is then obtained based on the transportation route planning information. And analyzing the path condition, calculating the transportation flow in unit time in different areas, and comparing the transportation flow with a preset threshold value to judge the path congestion condition. Based on the path condition analysis information, congestion diversion is carried out, the transportation flow of the adjacent area is extracted, and the path is adaptively changed by combining with the digital map so as to bypass the congestion road section and obtain diversion route information. The diversion route information is sent to the various transportation devices to guide them to avoid congested road segments, and in combination with digital maps, road segment marking and visualization of diversion routes are performed so that operators and drivers can better understand and follow new paths.

S108, acquiring throughput prediction information, predicting target port camping and analyzing resource utilization, and recommending an operation direction;

It should be noted that, first, the operation cost calculation is performed on the target port, including but not limited to equipment maintenance, fuel cost, personnel wages and equipment lease costs, so as to know the actual operation cost and help optimize the cost structure. And then, inputting port operation cost information and throughput prediction information into a port camp prediction model to predict the camp and obtain future camp prediction information of the port. Based on the accumulation condition analysis information and the equipment scheduling scheme, the utilization rate of the accumulation site and the equipment is calculated, and the resource utilization analysis is carried out to obtain the resource utilization condition analysis information so as to know the effective utilization condition of the port resources. The statistical algorithm is used for carrying out main business assessment on the port business attribute characteristic information, and the occurrence frequency of various business attributes is analyzed to be used as an assessment index so as to determine main business, such as loading, unloading, accumulation, transportation and the like. And then, acquiring port attribute information, and carrying out operation direction analysis by combining main service evaluation information and resource utilization analysis to judge whether a service direction capable of developing exists or not so as to obtain candidate operation direction analysis information. And acquiring port equipment information, acquiring demand equipment information of candidate operation directions based on big data retrieval, and comparing and analyzing the port equipment information and the demand equipment information to know the adaptation condition and the equipment lack condition of the equipment. And carrying out feasibility assessment on each candidate operation direction based on the requirement equipment adaptation analysis information. And selecting a final recommended operation direction according to the evaluation result to obtain operation direction recommended information, thereby providing operation direction advice which is more in line with the target port.

S110, acquiring recommendation information of the operation direction, analyzing situation of the target port, and pricing the recommendation direction.

It should be noted that, the maximum throughput is predicted through the daily operation information of the port, including the historical throughput, the cargo flow data, the ship scheduling, etc., and these data are input into the throughput prediction model to predict the maximum throughput that the port may realize, so as to understand the bearing capacity of the port and facilitate the planning of resources and equipment. Port operation characteristic information is an overview about the properties and historical operating conditions of the port itself. This includes the business area of the port, historical operation direction (such as cargo type, target market) and economic benefit of different operation directions, etc., so as to understand the basic characteristics of the port and past operation conditions. Next, an impact factor assessment is performed, taking into account a number of key factors, including historical customer information, competing port information (characteristics and services of other ports), and time, location, and cost factors. Then, through a multi-head attention mechanism, each factor is assigned an attention weight to learn which factors are important to decision making. This helps identify market trends and key success factors for ports. And then, based on influence factor evaluation information, historical customer information, competing port information and port operation characteristic information, SWOT analysis is performed based on a situation analysis method, so that a manager is helped to understand strategic positions of the port, and the internal advantages and disadvantages of the port, as well as external opportunities and threats are helped to be known. The pricing game model is used for determining price strategies of ports, simulating different price strategies and competition modes by considering operation direction recommendation information, influence factor evaluation information, situation analysis information and maximum throughput prediction information, predicting the influence of the price strategies and competition modes on the market, simulating the response of the market to the different price strategies according to a response function, including the change of market demands, the response of competing ports and the like, analyzing simulation results and judging with a preset threshold value to know which price strategy is most likely to be accepted by the market, so that the final price strategy is selected, the throughput and the profitability of the ports are improved, and higher benefits and resource utilization rate are brought to the ports.

As shown in FIG. 2, the present invention provides a pricing strategy flow chart comprising:

S202, carrying out field headquarters harvest prediction on a target port, judging the harbour harvest condition, and carrying out resource utilization analysis on the target port;

S204, analyzing main business of the target port, acquiring port attribute information, and analyzing the operation direction by combining the resource utilization analysis information;

S206, acquiring the information of the required equipment according to the recommended information of the candidate operation direction, comparing the information with the target port equipment, and analyzing whether the information meets the equipment requirement or not to acquire the information of the operation recommended direction;

s208, evaluating influence factors, analyzing influence factors of a historical client selecting a target port, and analyzing situation of the target port;

s210, obtaining competition demand information, obtaining pricing strategies through a pricing game model, carrying out market reaction simulation on each pricing strategy according to a reaction function, judging simulation results of each strategy, and selecting a final pricing strategy.

Further, acquiring real-time monitoring information of the ship at the target port, and carrying out ship target detection by combining the real-time monitoring information based on a target detection algorithm to obtain target detection information; acquiring target port business information and loading and unloading planning information, and extracting current-day ship visiting information and loading and unloading planning information of each ship according to the target port business information to obtain ship planning information; carrying out ship marking by combining the target detection information and the ship planning information, and carrying out track extraction on each ship according to the real-time monitoring information to obtain track extraction information and ship marking information; performing track evolution on each ship according to the track extraction information, analyzing and predicting the behavior trend of each ship, and obtaining ship behavior analysis information; calculating the sailing speed of the ship according to the real-time monitoring information of the ship, and calculating the ratio of the position change distance of the ship to the time in unit time to obtain the sailing speed information of the ship; acquiring a digital map of a target port, judging a ship running destination by combining the ship behavior analysis information and the ship marking information, and analyzing whether a route error exists or not to obtain ship route analysis information; generating route guide information according to the route analysis information and combining with a digital map of a target port, and sending the route guide information to a corresponding ship for guiding, so that accidents caused by route errors are avoided; presetting a sailing rate judgment threshold, judging the sailing rate information of the ship and the sailing rate judgment threshold, analyzing whether overspeed behaviors exist, and generating rate early warning information according to a judgment result; and acquiring the adjacent ships of the abnormal ships according to the ship marking information and the ship behavior analysis information, and sending the speed early warning information to the adjacent ships and the abnormal ships for early warning and reminding, so that route congestion and ship collision are avoided, and the safety of port operation is improved.

Fig. 3 is a block diagram 3 of an integrated port operation prediction system based on big data analysis according to an embodiment of the present invention, where the system includes: the comprehensive port operation prediction method based on big data analysis comprises a memory 31 and a processor 32, wherein the memory 31 contains the comprehensive port operation prediction method based on big data analysis, and the comprehensive port operation prediction method based on big data analysis realizes the following steps when being executed by the processor 32:

The invention provides a comprehensive port operation prediction method and a comprehensive port operation prediction system based on big data analysis, which are used for carrying out throughput prediction by analyzing service information of a target port. And comprehensively considering various factors such as current requirements, ship information and the like to estimate throughput in a future period of time. And then, acquiring port cargo information, analyzing cargo accumulation conditions, and carrying out ship loading and unloading planning according to analysis results, thereby effectively managing cargo flow and reducing congestion. And then, constructing a digital map of the target port, comprising the information of terrains, roads and facilities, planning a transportation route by utilizing the digital map so as to optimize the flow of cargoes and the dispatching of equipment, and carrying out real-time monitoring and congestion diversion to improve the transportation rate. And then, predicting target port camping by using throughput prediction information, judging port operation camping conditions by considering operation cost, and simultaneously, carrying out resource utilization analysis to know effective utilization conditions of port resources. Based on the resource utilization analysis and other relevant factors, an operational direction recommendation is provided. This may include recommendations for expanding the business field, improving the loading and unloading process, etc. And analyzing the situation of the target port, analyzing the dominant and disadvantaged threats and opportunities of the port, and effectively analyzing the market competitiveness of the port. And finally, pricing analysis is carried out, and an optimal price strategy is formulated so as to improve the competitiveness and attract more clients, and the operation efficiency and benefit of the port are improved.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.

The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.

Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. The comprehensive port operation prediction method based on big data analysis is characterized by comprising the following steps of:

acquiring operation direction recommendation information, carrying out situation analysis on a target port, and carrying out pricing analysis on the operation recommendation direction;

the construction of the digital map of the target port, and the planning of the transportation route and the formulation of the equipment scheduling scheme according to the digital map of the target port, specifically comprises the following steps:

2. The comprehensive port operation prediction method based on big data analysis according to claim 1, wherein the obtaining the target port service information and performing throughput prediction according to the target port service information specifically comprises:

3. The comprehensive port operation prediction method based on big data analysis according to claim 1, wherein the acquiring port cargo information, analyzing cargo accumulation conditions through the port cargo information, and performing ship loading and unloading planning according to analysis results specifically comprises:

4. The comprehensive port operation prediction method based on big data analysis according to claim 1, wherein the obtaining of throughput prediction information, performing target port revenue prediction and resource utilization analysis, and performing operation direction recommendation specifically comprises:

And carrying out feasibility evaluation on each candidate operation direction according to the required equipment adaptation analysis information, and selecting a final recommended operation direction according to an evaluation result to obtain operation direction recommendation information.

5. The comprehensive port operation prediction method based on big data analysis according to claim 1, wherein the obtaining operation direction recommendation information, performing situation analysis on a target port, and performing pricing analysis on an operation recommendation direction specifically comprises:

6. A comprehensive port operation prediction system based on big data analysis, the system comprising: the comprehensive port operation prediction method based on big data analysis comprises a memory and a processor, wherein the memory contains a comprehensive port operation prediction method program based on big data analysis, and when the comprehensive port operation prediction method program based on big data analysis is executed by the processor, the following steps are realized:

7. The comprehensive port operation prediction system based on big data analysis according to claim 6, wherein the obtaining the target port service information and performing throughput prediction according to the target port service information specifically comprises:

8. The comprehensive port operation prediction system based on big data analysis according to claim 6, wherein the acquiring port cargo information, analyzing cargo accumulation conditions through the port cargo information, and performing ship loading and unloading planning according to analysis results, specifically comprises: